Papers › TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition

TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition

24 Jul 2023ICCV 2023 1arXiv:2307.12493archive 2025-07-28

Shilin Lu, Yanzhu Liu, Adams Wai-Kin Kong

Text-driven diffusion models have exhibited impressive generative capabilities, enabling various image editing tasks. In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for cross-domain image-guided composition. This task aims to seamlessly integrate user-provided objects into a specific visual context. Current diffusion-based methods often involve costly instance-based optimization or finetuning of pretrained models on customized datasets, which can potentially undermine their rich prior. In contrast, TF-ICON can leverage off-the-shelf diffusion models to perform cross-domain image-guided composition without requiring additional training, finetuning, or optimization. Moreover, we introduce the exceptional prompt, which contains no information, to facilitate text-driven diffusion models in accurately inverting real images into latent representations, forming the basis for compositing. Our experiments show that equipping Stable Diffusion with the exceptional prompt outperforms state-of-the-art inversion methods on various datasets (CelebA-HQ, COCO, and ImageNet), and that TF-ICON surpasses prior baselines in versatile visual domains. Code is available at https://github.com/Shilin-LU/TF-ICON

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.12493")

Code

Syntology Ran 20 of 26 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · violated contract; 6 ran · our draft was wrong; 1 ran · fixture could not drive it; 10 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 14 ran; community (archive-listed): 11 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Shilin-LU/TF-ICON officialmentioned in papermentioned on GitHubpytorchMIT report
shilin-lu/vine mentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

26 samples harvested; 20 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · violated contract
6ran · our draft was wrong
1ran · fixture could not drive it
10ran
6unverified

Licence: 11 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Normalize Shilin-LU/TF-ICON/ldm/modules/diffusionmodules/model.py official repository ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report
append_dims Shilin-LU/TF-ICON/ldm/models/diffusion/sampling_util.py official repository ran MIT (permissive) · 082e51fd548d78b2 · report
default Shilin-LU/TF-ICON/ldm/modules/attention.py official repository ran · violated contract MIT (permissive) · 424012cb37b31172 · report
disabled_train Shilin-LU/TF-ICON/ldm/models/diffusion/ddpm.py official repository ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report
exists Shilin-LU/TF-ICON/ldm/modules/attention.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
get_timestep_embedding Shilin-LU/TF-ICON/ldm/modules/diffusionmodules/model.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · cb49209c125de1b4 · report
isimage Shilin-LU/TF-ICON/ldm/util.py official repository ran MIT (permissive) · b1368330cf0f5642 · report
ismap Shilin-LU/TF-ICON/ldm/util.py official repository ran MIT (permissive) · d72762b700feee6f · report
nonlinearity Shilin-LU/TF-ICON/ldm/modules/diffusionmodules/model.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report
norm_thresholding Shilin-LU/TF-ICON/ldm/models/diffusion/sampling_util.py official repository ran fingerprinted MIT (permissive) · 9898fe8b041f354c · report
spatial_norm_thresholding Shilin-LU/TF-ICON/ldm/models/diffusion/sampling_util.py official repository ran fingerprinted MIT (permissive) · d86694c13b94ae3a · report
text_under_image Shilin-LU/TF-ICON/ptp_scripts/ptp_utils.py official repository ran MIT (permissive) · 85d5eb123674597d · report
uniform_on_device Shilin-LU/TF-ICON/ldm/models/diffusion/ddpm.py official repository ran · our draft was wrong MIT (permissive) · d48d8354986e3b0e · report
uniq Shilin-LU/TF-ICON/ldm/modules/attention.py official repository ran · our draft was wrong MIT (permissive) · 9a299fe5ae09e407 · report
log_txt_as_img Shilin-LU/TF-ICON/ldm/util.py official repository unverified MIT (permissive) · f9bd2e83191afad1 · report
ConditionAdaptor shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran licence not identified · pointer only · 67766051714cc3f5 · report
Conv2D shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran fingerprinted licence not identified · pointer only · 32745d47d7d2e2d9 · report
Dense shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran licence not identified · pointer only · c3b3a2d8b7a04439 · report
VAE_encode shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran licence not identified · pointer only · 2e3c099f5b18d31d · report
my_vae_decoder_fwd shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · f7c07edb0eb5581a · report
my_vae_encoder_fwd shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 1f71b297e8da0a68 · report
VAE_decode shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) unverified licence not identified · pointer only · df3a01fb8f6ab1aa · report
VINE_Turbo shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) unverified licence not identified · pointer only · 8aae2565e1cd00e4 · report
initialize_unet_no_lora shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) unverified licence not identified · pointer only · 1d803d016f3caf34 · report
initialize_vae_no_lora shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) unverified licence not identified · pointer only · c7eede4c9a3fa0e7 · report
make_1step_sched shilin-lu/vine/vine/src/vine_turbo.py community (archive-listed) unverified licence not identified · pointer only · 19414a39b68285aa · report

Tasks

Image-Guided CompositionText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections